Vetted Workflow Orchestration Professionals

“Built and deployed a production LLM-based RAG agent platform adopted by multiple business teams (Marketing, GTM, Recruiting, Customer Support) to automate knowledge search, Q&A, and content generation. Emphasizes production-grade reliability (grounding/validation/guardrails), rigorous evaluation/monitoring, and cost-aware scaling via model tiering, prompt/retrieval optimization, and caching using LangChain/LangGraph orchestration.”

“ML/NLP practitioner who built a retrieval-augmented generation (RAG) system for large financial and operational document sets using Sentence-Transformers (all-mpnet-base-v2) and a vector DB (e.g., Pinecone), with a strong focus on retrieval evaluation and chunking strategy optimization. Experienced in entity resolution (rules + embedding similarity with type-specific thresholds) and in productionizing scalable Python data workflows using Airflow/Dagster and Spark.”

“Recent J&J intern who built a conversational RAG agent and led a shift from a monolithic model to a modular RAG workflow, cutting response time from several days to under a second by tackling data fragmentation, context retention, and embedding/latency optimization. Also worked on a large (7B-parameter) multimodal VQA pipeline for healthcare research and stays current via NeurIPS/ICLR and open-source contributions.”

“ML/AI practitioner with hands-on experience deploying models to production and optimizing for low-latency inference using pruning/quantization, with deployments on AWS SageMaker and Azure ML. Has orchestrated end-to-end ML pipelines with Airflow and Kubeflow (ingestion through evaluation) and emphasizes reproducibility via containerization and version-controlled artifacts, while effectively partnering with non-technical stakeholders using dashboards and business-aligned metrics.”

“Data/ML practitioner with experience at Airtel and Lincoln Financial delivering measurable business outcomes: improved retention 15% via NLP sentiment analysis and cut response time ~25% using sentence-BERT + FAISS semantic linking. Strong in data quality/identity resolution (SQL + fuzzy matching) and in building production-grade Python workflows orchestrated with Airflow/AWS Glue, including validation and dashboard integration in Power BI.”

“AI/ML engineer who has deployed transformer-based NLP systems to production via Python REST APIs and Kubernetes on AWS/Azure, with a strong focus on latency optimization (p95), reliability, and scalable orchestration. Demonstrates pragmatic model tradeoff decision-making and strong stakeholder collaboration—improving adoption by making outputs more actionable with summaries, extracted fields, and confidence indicators.”

“Full-stack engineer who built a cloud storage app feature (file upload/management) with Next.js App Router + TypeScript and owned post-launch improvements. Also has internship experience building a geospatial AI chatbot: designed Postgres/PostGIS data models and optimized spatial queries, and implemented an LLM workflow orchestrated with LangChain/LangGraph plus a RAG pipeline grounded in OpenStreetMap data to reduce hallucinations.”

“Data engineer focused on AWS-based enterprise data platforms, owning end-to-end pipelines from multi-source batch/stream ingestion (Glue/Kinesis/StreamSets/Airflow) through PySpark transformations into curated datasets for Redshift/Snowflake. Emphasizes production reliability with strong monitoring/observability and data quality gates, and reports ~30% performance improvement plus improved SLAs and latency after optimization.”

sudha kumari

Screened

Senior Full-Stack Product Engineer specializing in Next.js, TypeScript, and distributed systems

Frisco, Texas6y exp

“Full-stack engineer who built and shipped an analytics dashboard for search visibility using Next.js App Router/TypeScript with a server-components-first data strategy and server actions for interactivity. Designed and optimized the underlying Postgres analytics model and queries at scale, and implemented a durable Temporal-based indexing workflow with retries and idempotency—plus delivered a major frontend performance jump (Lighthouse low 70s to mid-90s).”

Teage Johnson

Screened

Junior Full-Stack Engineer specializing in FinTech and machine learning

California, USA3y exp

“Software engineer at early-stage startup Cari with hands-on experience shipping AI-enabled production workflows, including an LLM chatbot for a micro-transit platform and an automated image-processing pipeline integrated with Claude. Stands out for combining practical agent reliability patterns—schema validation, fallbacks, caching, and idempotency—with strong ML evaluation instincts and experience cleaning messy operational invoice data.”

Maryna Deundiak

Screened

Director-level Product Leader specializing in enterprise automation and platform integration

Florida, USA15y exp

“Product leader at Stellantis with a strong track record in large-scale digital transformation across automotive brands and markets. He combines platform modernization, UX simplification, and AI-enabled connected vehicle services to drive measurable outcomes, including a 30% lift in online bookings, while also mentoring cross-functional teams and future product leaders.”

“Full-stack engineer with early-stage startup experience who shipped and owned production Next.js (App Router + TypeScript) features end-to-end, including auth-aware APIs, caching, and post-launch monitoring/iteration. Demonstrates strong performance and reliability chops across React UX optimization, Postgres analytics modeling/query tuning (validated via query plans), and durable ingestion workflows with retries/idempotency.”

Yukta Chikate

Screened

Mid-level Machine Learning Engineer specializing in safety-critical and uncertainty-aware ML systems

Brooklyn, NY5y exp

“Built and productionized an LLM-powered assistant for company documents and support questions, focused on reducing time spent searching PDFs/policies/tickets while preventing hallucinations by grounding answers in approved sources. Demonstrates strong production engineering (Kubernetes/orchestration, caching, monitoring, fallbacks) plus security-minded permissioning and close collaboration with operations/support stakeholders.”

Ram Usarty

Screened

Mid-level Full-Stack Software Engineer specializing in cloud-native distributed systems

USA4y exp

“Backend/platform-focused engineer who has shipped production LLM agents for messy research dataset submissions, turning manual validation into an automated, reliable ingestion pipeline. Strong on production hardening (streaming large uploads, strict schema/function-calling outputs, idempotency, RBAC) plus eval/monitoring loops that improved data quality, reduced support burden, and increased adoption.”

“Lead full stack Java developer with deep experience building compliance-sensitive government financial systems, including payment distribution, escrow hold management, reallocations, and disbursement workflows. Stands out for combining Angular/React frontend work with Spring Boot, Oracle SQL/PL-SQL, and batch/JMS architecture to stabilize high-volume transaction systems, automate manual workflows, and reduce production support issues.”

“Built and shipped a production RAG-based enterprise knowledge assistant to replace slow/inaccurate search across millions of documents, using LangChain orchestration with GPT-4/LLaMA and vector databases. Strong focus on production constraints—latency, hallucination control, and cost—using hybrid retrieval, guardrails, LLM-as-judge validation, and model routing, and has experience translating non-technical stakeholder pain points into measurable outcomes.”

“Built and deployed a production SecureAIChatBot (RAG-based) for secure internal information retrieval, using embeddings/vector search, GPT models, monitoring, and safety filters. Focused on real-world production challenges like latency and output consistency, applying caching, retrieval scoping, smaller models, and controlled prompting, and used LangChain to orchestrate the end-to-end workflow.”